AI Paper Atlas

Research map / Point clouds / Point cloud classification

FH-Net: A Fast Hierarchical Network for Scene Flow Estimation on Real-World Point Clouds

Lihe Ding, Shaocong Dong, Tingfa Xu, Xinli Xu, Jie Wang, Jianan Li

ECCV 2022 · Point clouds › Point cloud classification · approach: Scene flow and dynamic point clouds · 12 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add Trans-up layer (with feature interaction) in place of linear interpolation upsampling (ablation)FH-L · Lidar-KITTI (trained on SF-KITTI)EPE3D: 0.459 -> 0.255Improved
add feature interaction to the Trans-up layer (ablation)FH-L · Lidar-KITTI (trained on SF-KITTI)EPE3D: 0.314 -> 0.255Improved
add hierarchical loss on intermediate flows (ablation)FH-L · Lidar-KITTI (trained on SF-KITTI)EPE3D: 0.306 -> 0.265Improved
raise foreground weight to 5 and background to 0.5 in hierarchical loss (ablation)FH-L · Lidar-KITTI (trained on SF-KITTI)EPE3D: 0.265 -> 0.255Improved
use Trans-flow layer instead of averaging candidate flows (ablation)FH-L · Lidar-KITTI (trained on SF-KITTI)EPE3D: 1.384 -> 0.255Improved
use Trans-flow layer instead of nearest point offset (ablation)FH-L · Lidar-KITTI (trained on SF-KITTI)EPE3D: 1.025 -> 0.255Improved
add position encoding in Trans-flow layer (ablation)FH-L · Lidar-KITTI (trained on SF-KITTI)EPE3D: 0.278 -> 0.255Improved
add residual flow refinement in flow propagation (ablation)FH-L · Lidar-KITTI (trained on SF-KITTI)EPE3D: 0.255 -> 0.223Improved
add copy-and-paste augmentation with 3 cars, 1-5 pedestrians, 1-4 cyclists (ablation)FH-L · Lidar-KITTI (trained on SF-KITTI), overall EPE3DEPE3D: 0.308 -> 0.255Improved
add copy-and-paste augmentation with 3 cars, 1-5 pedestrians, 1-4 cyclists (ablation)FH-L · Lidar-KITTI (trained on SF-KITTI), foregroundforeground EPE3D: 0.278 -> 0.127Improved
increase pasted cars from 3 to 6 (ablation)FH-L · Lidar-KITTI (trained on SF-KITTI)EPE3D: foreground 0.127 -> 0.106; overall 0.255 -> 0.259Mixed
train FH-L on SF-Waymo instead of FT3D (ablation)FH-L · SF-Waymo/evalEPE3D: 0.673 -> 0.243Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 4 of 4 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy